Cargando…
Physics Object Localization with Point Cloud Segmentation Networks
In modern particle physics experiments, the identification and trajectory of physics object, e.g. leptons and jets, depends on a complex pipeline of feature extraction, search, and machine learning algorithms. Deep neural networks (DNNs) offer a possibility of streamlining this process. This note de...
Autor principal: | The ATLAS collaboration |
---|---|
Lenguaje: | eng |
Publicado: |
2021
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2753414 |
Ejemplares similares
-
Point Cloud Deep Learning Methods for Pion Reconstruction in the ATLAS Experiment
por: The ATLAS collaboration
Publicado: (2022) -
Proposal for particle-level object and observable definitions for use in physics measurements at the LHC
por: The ATLAS collaboration
Publicado: (2015) -
METNet: A combined $p^{\text{miss}}_{\text{T}}$ working point using a neural network with the ATLAS detector
por: The ATLAS collaboration
Publicado: (2021) -
Object-based missing transverse momentum significance in the ATLAS detector
por: The ATLAS collaboration
Publicado: (2018) -
Boosted Object Tagging with Variable-$R$ Jets in the ATLAS Detector
por: The ATLAS collaboration
Publicado: (2016)